Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    polynomial features

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ну
    -0.09
    ニュース
    -0.08
     Alma
    -0.08
     تحقیقات
    -0.08
     معت
    -0.08
     imped
    -0.08
     淮
    -0.08
     unmar
    -0.08
    .rabbit
    -0.08
    論
    -0.07
    POSITIVE LOGITS
     projectile
    0.09
     Expand
    0.08
     skyline
    0.08
    Expanded
    0.08
     Expanded
    0.08
     expand
    0.08
    sit
    0.08
    -expand
    0.08
    expand
    0.08
     GC
    0.08
    Act Density 0.004%

    No Known Activations